← Back to all news
arXiv Machine Learning By Zirui Wan, Stefan Vlaski

Decentralized Multitask Learning over Learned Task Graphs

Read the original on arXiv Machine Learning →

The paper presents a decentralized multitask learning framework that learns task relationships directly from distributed data. It introduces a two‑phase strategy: first estimating a generalized graph Laplacian from noisy stochastic gradient iterates, then using the learned graph to facilitate cooperative multitask diffusion learning. The authors provide theoretical analysis of Laplacian estimation error, its impact on steady‑state performance, and a topology sensitivity index, and confirm the benefits of learned task graphs through simulations.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
3d ago

Connectivity-Aware Client Selection in Decentralized Federated Learning

The paper introduces connectivity-aware client selection for decentralized federated learning, using spectral graph tools to choose a subset of structurally relevant neighbors for each client. By leveraging eigenvector embeddings and heat/diffusion kernel similarities, the method reduces communication overhead while maintaining or improving accuracy compared to uniform subsampling and full broadcasting. Experiments show up to a 3‑percentage‑point accuracy gain under strong data heterogeneity and a 50% reduction in transmitted messages.

By Usevalad Milasheuski, Monica Nicoli, Stefano Savazzi
ragdiffusion
More like this →
arXiv AI
Oct 5

Cordial Learning: Distributed Training with Correlated Data

The paper introduces cordial learning, a distributed training framework for agents with correlated data, where each agent’s label depends on inputs from other agents. By sharing only low‑dimensional outputs, agents train local models that extract informative signals from peers, forming a game‑theoretic loss that depends on others’ models. The authors prove convergence to a globally optimal solution for linear models and show empirical effectiveness on structured multi‑digit MNIST tasks, even in nonlinear settings.

By Sarah Shitrit, Ilai Bistritz
agentssafety
More like this →
arXiv Machine Learning
Oct 15

A Large-Dimensional Analysis of Least-Squares Federated Learning via Generalized Total Variation Minimization

The paper presents a large‑dimensional analysis of Generalized Total Variation Minimization (GTVMin) for least‑squares federated learning. It shows that Lipschitz observations of the global GTVMin solution concentrate in high dimensions regardless of network structure, and derives exact analytic expressions for performance under both i.i.d. and non‑i.i.d. Gaussian mixture models. These results quantify how regularization balances local adaptation against collaboration, and are validated by experiments on synthetic and real‑world data.

By Ekkehard Schnoor, Malik Tiomoko, Alexander Jung
safety
More like this →